© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62984
    Prev
    Next
    INDEX
    Explanations

    future, time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spo
    -0.26
    ASA
    -0.25
    ways
    -0.25
    èĪ¬çļĦ
    -0.25
    éĤ£æł·çļĦ
    -0.25
    worthy
    -0.25
    ä»Ĭ天çļĦ
    -0.24
    æľīåħ´è¶£
    -0.24
    æľįåĬ¡èĥ½åĬĽ
    -0.23
    ACY
    -0.23
    POSITIVE LOGITS
    æ¦Ĥ
    0.31
    taire
    0.31
     undert
    0.27
    Foot
    0.27
    aghan
    0.27
    Warm
    0.26
     du
    0.26
     restraining
    0.25
    à¹ĥà¸Ī
    0.25
    æįī
    0.25
    Activations Density 11.169%

    No Known Activations